High-risk tools in Meshy MCP Server
4 of the 20 tools in Meshy MCP Server are classified as high risk. This page profiles those tools specifically, with recommended policy actions and the attack patterns that target them.
Every operation listed below is an action PolicyLayer recommends controlling at the transport layer. Open any tool to see the full profile, risk score, and YAML policy snippet.
Tools at high risk
-
meshy_image_to_imageExecuteTransform images using AI with a text prompt and reference images using Meshy AI. Reference Image Input (provide ONE of these): - reference_image_urls (array): 1–5 publicly a...
-
meshy_remeshExecuteRemesh an existing 3D model or convert it to different formats using Meshy AI. Use this to optimize polygon count, change topology, convert formats, or reposition model origin....
-
meshy_text_to_imageExecuteGenerate a 2D image from a text description using Meshy AI. Useful for creating reference images that can then be used with image-to-3d or image-to-image. Args: - ai_model (...
-
meshy_send_to_slicerExecuteDetect installed 3D printing slicer software and return launch commands. IMPORTANT: This tool should be called as the FIRST STEP in any 3D printing workflow — before generating...
Attacks that target this class
High-risk tools in any server share these documented attack patterns. Each links to the full case and the defensive policy.